
Memory Bank MCP Server
Provides a structured documentation system for context preservation in AI assistant environments, helping users create and manage memory banks for their projects.
README
Memory Bank MCP Server
This MCP server provides a structured documentation system for context preservation in AI assistant environments.
Powered by Enlighter and Hyperskill
Features
- Get detailed information about Memory Bank structure
- Generate templates for Memory Bank files
- Analyze project and provide suggestions for Memory Bank content
Running the Server
There are a few options to use this MCP server:
With Smithery
Add this to your mcp.json config file:
{
"mcpServers": {
"memory-bank": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@ipospelov/mcp-memory-bank",
"--key",
"your_smithery_key"
]
}
}
}
With SSE
Add this to your mcp.json config file:
{
"mcpServers": {
"memory-bank": {
"url": "https://mcp-cursor-setup-enlighter.replit.app/sse"
}
}
}
With Docker
Add this to your mcp.json config file:
{
"mcpServers": {
"memory-bank": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"mcp-memory-bank"
]
}
}
}
Manually
Run the following commands:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
Then add this to your mcp.json config file:
{
"mcpServers": {
"memory-bank": {
"command": "python",
"args": ["server.py"]
}
}
}
Usage Example
Ask Cursor or any other AI code assistant with Memory Bank MCP:
Create memory bank for To Do list application with your tools
Provide more context to get better results.
Available Tools
get_memory_bank_structure
Returns a detailed description of the Memory Bank file structure.
generate_memory_bank_template
Returns a template for a specific Memory Bank file.
Example:
{
"file_name": "projectbrief.md"
}
analyze_project_summary
Analyzes a project summary and provides suggestions for Memory Bank content.
Example:
{
"project_summary": "Building a React web app for inventory management with barcode scanning"
}
Memory Bank Structure
The Memory Bank consists of core files and optional context files, all in Markdown format:
Core Files (Required)
projectbrief.md
- Foundation document that shapes all other filesproductContext.md
- Explains why the project exists, problems being solvedactiveContext.md
- Current work focus, recent changes, next stepssystemPatterns.md
- System architecture, technical decisions, design patternstechContext.md
- Technologies used, development setup, constraintsprogress.md
- What works, what's left to build
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。